Inference-Friendly Models with MixAttention
Transformer models, the backbone of modern language AI, rely on the attention mechanism to process context when generating output. During inference, the attention...
Page 1
>
A Pattern for the Lightweight Deployment of Distributed XGBoost and LightGBM Models
A common challenge data scientists encounter when developing machine learning solutions is training a model on a dataset that is too large to...
Automated Analysis of Product Reviews Using Large Language Models (LLMs)
Check out our LLM Solution Accelerators for Retail for more details and to download the notebooks. While conversational AI has garnered a lot...
Using MLflow AI Gateway and Llama 2 to Build Generative AI Apps
To build customer support bots, internal knowledge graphs, or Q&A systems, customers often use Retrieval Augmented Generation (RAG) applications which leverage pre-trained models...
Synthetic Data for Better Machine Learning
You've likely tried the buzziest advances in generative AI in the past year, tools like ChatGPT and DALL-E . They consume complex data...
Fine-Tuning Large Language Models with Hugging Face and DeepSpeed
Large language models (LLMs) are currently in the spotlight following the sensational release of ChatGPT. Many are wondering how to take advantage of...
Mitigating Bias in Machine Learning With SHAP and Fairlearn
Try this notebook in Databricks. With good reason, data science teams increasingly grapple with questions of ethics, bias and unfairness in machine learning...
How (Not) to Tune Your Model With Hyperopt
Hyperopt is a powerful tool for tuning ML models with Apache Spark. Read on to learn how to define and execute (and debug)...
Better Machine Learning through Active Learning
Try this notebook to reproduce the steps outlined below Machine learning models can seem like magical savants. They can distinguish hot dogs from...
How (Not) To Scale Deep Learning in 6 Easy Steps
Try this notebook in Databricks Introduction: The Problem Deep learning sometimes seems like sorcery. Its state-of-the-art applications are at times delightful and at...